What’s a query pipeline?

This is for:

In this article

Order of execution
What’s next?

In your Coveo organization, a query pipeline is an alternate set of rules or model associations that can be defined to modify queries. You can define query pipelines from the Coveo Administration Console (see Manage query pipelines).

You can take advantage of query pipelines when you have more than one search interface with distinct users and purposes and want to apply different rules or models for each.

Example

Your customers and partners use your community portal to self-serve and find relevant information, while your support agents access an internal service portal to find relevant public and private items. You can create a separate pipeline for each portal, defining appropriate rules for each search interface audience.

You can also use query pipeline A/B testing to evaluate rule or model changes on a part of the users.

Query pipeline rules can define:

Search terms
- Thesaurus entries - replacing or expanding queries with synonyms.
- Stop words - ignoring unimportant words in queries.
Result rankings
- Featured results - items appearing at the top of search results when the query meets a specific condition.
- Ranking expressions - modifying the order of results matching specified expressions and conditions.
Groups & campaigns - grouping sets of result ranking rules that apply for specific contexts, audiences, or periods of time.
Advanced query pipeline rules
- Filters - adding hidden query expressions to all queries that go through the query pipeline.
- Query parameters - overriding search parameter values for every query that goes through the query pipeline.
- Ranking weights - establishing the impact of ranking factors when establishing the order of results.
- Triggers - establishing actions to be performed in the user search interface following an event when a condition is met.

Query pipeline associated models can define:

Relevance Generative Answering (RGA) - generating answers to complex user queries using generative AI technology.
Semantic Encoder (SE) - optimizing search results relevance based on semantic similarity using vector-based search.
Automatic Relevance Tuning (ART) - optimizing search results relevance based on user search behavior.
Query Suggestions (QS) and Predictive Query Suggestions (PQS) - suggesting queries to users as they type in a search box.
Content Recommendations (CR) - predicting and proposing the most relevant content for the current user in the current session.
Dynamic Navigation Experience (DNE) - reordering facets and facet values to place the most relevant at the top.
Product Recommendations (PR) - relevantly suggest products to end users navigating Coveo-powered commerce solutions.
Intent-Aware Product Ranking (IAPR) - ranking products on a search results page based on the visitor’s shopping intent.
Smart Snippets - displaying a snippet of the most relevant result item directly on the results page.

See Manage models.

The features you define in a query pipeline are applied to all queries before they’re sent to the index.

Order of execution

The following diagram illustrates the overall order of execution of query pipeline features:

What’s next?

Understand how to create and use a query pipeline (see Deploy a query pipeline).